Voice Recognition Based on Vector Quantization Using LBG

Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 5)

Abstract

The process which recognizes the speaker based on the information present in the speech is called Voice recognition. This can be used to many applications like identification, voice dialling, tele-shopping, voice based access services, information services, tele-banking, security control of confidential information. The variation of Speaker exists in speech signals because of different resonances of the vocal tract. MFCC is the technique to exploit the differences of the speech signal. Similarly, the technique of Vector Quantization (VQ) emerged as useful tool. In this chapter, the VQ is employed for efficient creating the extracted feature vector. The acoustic vectors extracted from input speech of a speaker and provide a set of training vectors. LBG algorithm is used for clustering a set of L training vectors into a set of M codebook vectors.

Keywords

Speech processing Vector quantization LBG algorithm MFCC 

References

  1. 1.
    Kekre, H.B., Vaishali, Kulkarni: Speaker Identification by using Vector Quantization. Intl J of Engg Sc and Tech, vol. 2, pp. 1325–1331 (2010)Google Scholar
  2. 2.
    Linde, Y., Buzo, A., Gray, R.: An algorithm for vector quantizer design. IEEE Trans on Comm, vol. 28, pp. 84–95 (1980)Google Scholar
  3. 3.
    Rita Singh, Bhiksha Raj, Stern, R.M: Automatic Generation of Sub word Units for Speech Recognition Systems. IEEE Trans on speech and audio processing. Vol. 10 (2002)Google Scholar
  4. 4.
    Jesus Savage, Carlos Rivera, Vanessa Aguilar, “Isolated Word Speech Recognition Using Vector Quantization Techniques and Artificial Neural Networks”, Facultad de Ingenieria, Departamento de Ingeniería en Computación, University of Mexico, UNAM, Mexico City C.P. 04510, Mexico (1994)Google Scholar
  5. 5.
    Rabiner. L. R, Juang, B.H.: Fundamentals of Speech Recognition, Prentice-Hall, Englewood Cliffs, N.J (1993)Google Scholar
  6. 6.
    Tzu-Chuen Lu, Ching-Yun Chang, “A Survey of VQ Codebook Generation”, Journal of Information Hidingand Multimedia Signal Processing, Ubiquitous International, Vol. 1, No. 3, pp. 190–203, (2010)Google Scholar
  7. 7.
    Furui. S, Speaker-independent isolated word recognition using dynamic features of speech spectrum, IEEE Trans on Acoustic, Speech, Signal Processing, Vol. 34, pp. 52–59, (1986)Google Scholar
  8. 8.
    Furui. S.: An overview of speaker recognition technology, ESCA Workshop on Automatic SpeakerRecognition, Identification and Verification, pp. 1–9, (1994)Google Scholar
  9. 9.
    Soong, F. E., Rosenberg, A. E., Juang, B. H.: A vector quantization approach to speaker recognition, AT & TTechnical Journal, Vol. 66, No. 2, pp. 14–26, (1987)Google Scholar
  10. 10.
    Wiploa J. G., Rabiner L. R.: A Modified K-Means Clustering Algorithm for Use in Isolated Word Recognition, IEEE Trans on Acoustics, Speech and Signal Processing, Vol. 33 No.3, pp. 587–594, (1985)Google Scholar
  11. 11.
    Marcel R. Ackermann, Johannes Blomer, Christian Sohler,: Clustering for Metric and Nonmetric DistanceMeasures, ACM Transactions on Algorithms, Vol. 6, No. 4, Article 59, pp. 1–26, (2010)Google Scholar
  12. 12.
    Shih-Ming Pan, Kuo-Sheng Cheng,: An evolution-based tabu search approach to codebook design, PatternRecognition, Vol. 40, No. 2, pp. 476–491, (2007)Google Scholar
  13. 13.
    Chin-Chen Chang, Yu-Chiang Li, Jun-Bin Yeh,: Fast codebook search algorithms based on tree-structuredvector quantization, Pattern Recognition Letters, Vol. 27, No. 10, pp. 1077–1086, (2006)Google Scholar
  14. 14.
    Buzo, Gray, A.H., Gray, R.M., Markel, J. D.,: Speech coding based upon vector quantization, IEEE Trans on Acoustics, Speech and Signal Processing, Vol. 28, No. 5, pp. 562–574, (1980)Google Scholar
  15. 15.
    Linde, Y., Buzo, A., Gray, R. M.,: An algorithm for vector quantizer design, IEEE Transactions on Communications, Vol. 28, No.1, pp. 84–95 (1980)Google Scholar
  16. 16.
    Modha, D., Spangler. S.,: Feature weighting in k-means clustering. Machine Learning, Vol. 52, No.3, pp. 217–237, (2003)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2017

Authors and Affiliations

  1. 1.ECE DepartmentVardhaman College of EngineeringShamshabadIndia
  2. 2.Department of ECEUniversity College of Engineering and Technology, Acharya Nagarjuna UniversityGunturIndia

Personalised recommendations